view r-gpca.xml @ 4:ceaa4d404115 draft default tip

planemo upload for repository https://github.com/blankenberglab/galaxy-tools-blankenberg/tree/master/tools/r-gpca commit 9ad682131963a72c88a5af1cfc99f90ea9d42a08

<tool id="gpca" name="gPCA" version="1.0.0">
  <description>Batch Effect Detection via Guided Principal Components Analysis</description>
    <requirements>
        <requirement type="package" version="1.0">r-gpca</requirement>
        <requirement type="package" version="1.6.0">r-optparse</requirement>
    </requirements>
    <version_command><![CDATA[Rscript '$__tool_directory__/r-gpca.R' --version]]></version_command>
    <command detect_errors="exit_code">
    <![CDATA[
      
      Rscript '$__tool_directory__/r-gpca.R'
        -i '${batch}'
        -d '${data}'
        -n '${nperm}'
        ${center}
        ${scaleY}
        #if str($filt):
            -f '${filt}'
        #end if
        #if str($seed):
            -s '${seed}'
        #end if
        --npcs '${npcs}'
        -p '${html_outfile.extra_files_path}'
        -x '${numbers_outfile}'
        -o '${html_outfile}';

    ]]></command>
    
    <inputs>
        <param type="data" name="data"  argument="--data" format="tabular"   label="Data input file" />
        <param type="data" name="batch" argument="--batch" format="tabular" label="Batch input file" />
        <param type="integer" name="nperm" argument="--nperm" value="1000" help="default=1000" label="Number of permutations to preform"/>
        <param type="boolean" name="center" argument="--center" checked="false" truevalue="--center" falsevalue="" help="Set to true to prevent gPCA from centering" label="Is the data centered?"/>
        <param type="boolean" name="scaleY" argument="--scaleY" checked="false" truevalue="--scaleY" falsevalue="" help="default=No" label="Should Y be scaled based on number of samples in each batch?"/>
        <param type="integer" name="filt" optional="true" argument="--filt"  min="1" value="" label="How many features to keep?" help="Leave blank for default(NULL)"/>
        <param type="integer" name="seed" optional="true" argument="--seed"  min="1" value="" label="Seed #" help="Leave blank for default(NULL)"/>
        <param type="integer" name="npcs" optional="false" argument="--npcs"  min="3" value="3" label="Principal Components to calculate" help="Number of principal components to calcualte"/>
    </inputs>

    <outputs>
        <data name="html_outfile" format="html" label="${tool.name} on ${on_string} html"/>
        <data name="numbers_outfile" format="tabular" label="${tool.name} on ${on_string}: values" />
    </outputs>

    <tests>
      <test>
        <param name="batch" ftype="tabular" value="batch_in_1.tabular"  />
        <param name="data" ftype="tabular" value="data_in_1.tabular"  />
        <param name="nperm" value="1000" />
        <param name="center" value="False" />
        <param name="scaleY" value="False" />
        <param name="filt" value="" />
        <param name="npcs" value="3" />
        <param name="seed" value="123456" />
        <output name="html_outfile" ftype="html" file="html_outfile_1/html_outfile_1.html">
          <extra_files type="file" name="gDist_1.png" value="html_outfile_1/gDist_1.png" compare="sim_size"/>
          <extra_files type="file" name="guided_1v2_1.png" value="html_outfile_1/guided_1v2_1.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_1v2_1.png" value="html_outfile_1/unguided_1v2_1.png" 
            compare="sim_size"/>
          <extra_files type="file" name="guided_npcs_1.png" value="html_outfile_1/guided_npcs_1.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_npcs_1.png" value="html_outfile_1/unguided_npcs_1.png" 
            compare="sim_size"/>
          <extra_files type="file" name="guided_var_1.png" value="html_outfile_1/guided_var_1.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_var_1.png" value="html_outfile_1/unguided_var_1.png" 
            compare="sim_size"/>
        </output>
        <output name="numbers_outfile" ftype="tabular" file="numbers_outfile_1.tabular"/>
      </test>
      <test>
        <param name="batch" ftype="tabular" value="batch_in_multiple_1.tabular"  />
        <param name="data" ftype="tabular" value="data_in_1.tabular"  />
        <param name="nperm" value="1000" />
        <param name="center" value="False" />
        <param name="scaleY" value="False" />
        <param name="filt" value="" />
        <param name="npcs" value="3" />
        <param name="seed" value="123456" />
        <output name="html_outfile" ftype="html" file="html_outfile_2/html_outfile_2.html">
          <extra_files type="file" name="gDist_1.png" value="html_outfile_2/gDist_1.png" compare="sim_size"/>
          <extra_files type="file" name="gDist_2.png" value="html_outfile_2/gDist_2.png" compare="sim_size"/>
          <extra_files type="file" name="guided_1v2_1.png" value="html_outfile_2/guided_1v2_1.png" compare="sim_size"/>
          <extra_files type="file" name="guided_1v2_2.png" value="html_outfile_2/guided_1v2_2.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_1v2_1.png" value="html_outfile_2/unguided_1v2_1.png" 
            compare="sim_size"/>
          <extra_files type="file" name="unguided_1v2_2.png" value="html_outfile_2/unguided_1v2_2.png" 
            compare="sim_size"/>
          <extra_files type="file" name="guided_npcs_1.png" value="html_outfile_2/guided_npcs_1.png" compare="sim_size"/>
          <extra_files type="file" name="guided_npcs_2.png" value="html_outfile_2/guided_npcs_2.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_npcs_1.png" value="html_outfile_2/unguided_npcs_1.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_npcs_2.png" value="html_outfile_2/unguided_npcs_2.png" compare="sim_size"/>
          <extra_files type="file" name="guided_var_1.png" value="html_outfile_2/guided_var_1.png" compare="sim_size"/>
          <extra_files type="file" name="guided_var_2.png" value="html_outfile_2/guided_var_2.png" compare="sim_size"/>
          <extra_files type="file" name="unguided_var_1.png" value="html_outfile_2/unguided_var_1.png" 
            compare="sim_size"/>
          <extra_files type="file" name="unguided_var_2.png" value="html_outfile_2/unguided_var_2.png" 
            compare="sim_size"/>
        </output>
        <output name="numbers_outfile" ftype="tabular" file="numbers_outfile_2.tabular"/>
      </test>
    </tests>
    
    <help>
      <![CDATA[

      **What it does**
      Utilizes guided principal components analysis for the detection of batch effects in high-throughput data.

      Arguments:

      batch: a length n vector that indicates batch (group or class) for each observation.

      x/data:  an nxp matrix of data where n denotes observations and p denotes the numberof features (e.g. probe, gene, SNP, etc.).

      filt:  (optional) the number of features to retain after applying a variance filter. If NULL,  no  filter  is  applied. Filtering  can  significantly  reduce  the  processing time in the case of very large data sets.

      nperm: the number of permutations to perform for the permutation test, default is 1000.

      center:  (logical) Is your data x centered? If not, then center=FALSE and gPCA.batchdetect will center it for you.

      scaleY:  (logical) Do you want to scale the Y matrix by the number of samples in each batch? If not, then center=FALSE (default), otherwise, center=TRUE.

      seed:  the seed number for set.seed(). Default is NULL.

      npcs: number of principal components to calculate

      **Literature**
      https://cran.r-project.org/web/packages/gPCA/gPCA.pdf

      https://cran.r-project.org/web/packages/gPCA/vignettes/gPCA.pdf
      
      **Input File Help**
      Batch: The batch file must be a tab delimited file.  It will be read as a numeric vector, consisting of as many different batches as you like.  The test data file batch_in_multiple_1.tabular shows the correct format.  The length of batch must conform to the data matrix or an error will occur.

      Data: The data file must be a tab delimited file.  It will be read in as a matrix.  The test data file data_in_1.tabular shows the correct format.  If you are receving errors about nonconformed matrices in your matrix you might need to transpose your matrix before using it in the tool.

      ]]>
    </help>
    
  <citations>
    <citation type="doi">10.1093/bioinformatics/btt480</citation>
    <citation type="bibtex">@unpublished{gpca:2018,
      title  = "gPCA Galaxy Tool",
      author = "Chris Lowe, Daniel Blankenberg",
      url    = "https://github.com/BlankenbergLab/galaxy-tools-blankenberg/tree/master/tools/r-gpca",
      year   = "2018 (accessed November 16, 2018)"}
    </citation>
  </citations>
</tool>